New issue 2322: Z SIMD Support https://bitbucket.org/pypy/pypy/issues/2322/z-simd-support
Richard Plangger: The goal is to enhance the backend to support s390x's SIMD unit. Ultimately this will enhance the execution speed of micro NumPy. What to expect: As soon as enough time is spent in the optimized (vectorized) code, one can measure faster execution. For a micro benchmark stressing the implementation it would be a factor of 1.5x-2.0x speedup for e.g. float (64bit) addition/multiplication. A benchmark run will evaluate the implementation on s390x and compare it to x86. Responsible: plan_rich _______________________________________________ pypy-issue mailing list pypy-issue@python.org https://mail.python.org/mailman/listinfo/pypy-issue
